Neural Network Weight
A Neural Network Weight is a Artificial Neural Network Parameter that is associated with a Artificial Neural Connection.
- AKA: Artificial Neural Network Weight, Synaptic Weight, Weight Activity, Synaptic Strength.
- Context:
- It is an element of Neural Network Weight Matrix which values are determined by a weight function.
- Example(s):
- In a Single Layer Neural Network with 3 neuron inputs and a signal neuron mathematecally described by [math]y=f(w_1x_1+w_2x_2+w_3x_3+b)[/math] and represented by
[math]w_1[/math], [math]w_2[/math], and [math]w_3[/math] are the 3 weights associated with each artificial neural connection.
- In a Single Layer Neural Network with [math]n[/math] neuron inputs and [math]p[/math] neurons, graphically represented as:
each element the matrix [math]w_{ij}[/math] is a neural network weight associated with the respective artificial neural connection.
- …
- In a Single Layer Neural Network with 3 neuron inputs and a signal neuron mathematecally described by [math]y=f(w_1x_1+w_2x_2+w_3x_3+b)[/math] and represented by
- Counter-Example(s):
- See: Neuron Activation Function, Neural Network Weight Matrix, Artificial Neuron, Artificial Neural Network, Neural Network Memory Cell, Neural Network Layer.
References
1998
- (Wilson,1998) ⇒ Bill Wilson, (1998 - 2012). "Weight" in "The Machine Learning Dictionary".
- QUOTE: weight: A weight, in a artificial neural network, is a parameter associated with a connection from one neuron, M, to another neuron N. It corresponds to a synapse in a biological neuron, and it determines how much notice the neuron N pays to the activation it receives from neuron N. If the weight is positive, the connection is called excitatory, while if the weight is negative, the connection is called inhibitory. See also to a neuron.
